scholarly journals Modified GAN Augmentation Algorithms for the MRI-Classification of Myocardial Scar Tissue in Ischemic Cardiomyopathy

2021 ◽  
Vol 8 ◽  
Author(s):  
Umesh C. Sharma ◽  
Kanhao Zhao ◽  
Kyle Mentkowski ◽  
Swati D. Sonkawade ◽  
Badri Karthikeyan ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Binary Classification ◽  
Coronary Revascularization ◽  
Scar Tissue ◽  
Myocardial Scar ◽  
Automated Classification ◽  
Multicenter Studies ◽  
Generative Adversarial Network ◽  
Therapeutic Decisions

Contrast-enhanced cardiac magnetic resonance imaging (MRI) is routinely used to determine myocardial scar burden and make therapeutic decisions for coronary revascularization. Currently, there are no optimized deep-learning algorithms for the automated classification of scarred vs. normal myocardium. We report a modified Generative Adversarial Network (GAN) augmentation method to improve the binary classification of myocardial scar using both pre-clinical and clinical approaches. For the initial training of the MobileNetV2 platform, we used the images generated from a high-field (9.4T) cardiac MRI of a mouse model of acute myocardial infarction (MI). Once the system showed 100% accuracy for the classification of acute MI in mice, we tested the translational significance of this approach in 91 patients with an ischemic myocardial scar, and 31 control subjects without evidence of myocardial scarring. To obtain a comparable augmentation dataset, we rotated scar images 8-times and control images 72-times, generating a total of 6,684 scar images and 7,451 control images. In humans, the use of Progressive Growing GAN (PGGAN)-based augmentation showed 93% classification accuracy, which is far superior to conventional automated modules. The use of other attention modules in our CNN further improved the classification accuracy by up to 5%. These data are of high translational significance and warrant larger multicenter studies in the future to validate the clinical implications.

scholarly journals An Imbalanced Image Classification Method for the Cell Cycle Phase

Information ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 249
Author(s):  
Xin Jin ◽  
Yuanwen Zou ◽  
Zhongbing Huang
Keyword(s):  
Cell Cycle ◽  
Deep Learning ◽  
Image Classification ◽  
Classification Accuracy ◽  
Data Augmentation ◽  
Cycle Phase ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Cellular Life

The cell cycle is an important process in cellular life. In recent years, some image processing methods have been developed to determine the cell cycle stages of individual cells. However, in most of these methods, cells have to be segmented, and their features need to be extracted. During feature extraction, some important information may be lost, resulting in lower classification accuracy. Thus, we used a deep learning method to retain all cell features. In order to solve the problems surrounding insufficient numbers of original images and the imbalanced distribution of original images, we used the Wasserstein generative adversarial network-gradient penalty (WGAN-GP) for data augmentation. At the same time, a residual network (ResNet) was used for image classification. ResNet is one of the most used deep learning classification networks. The classification accuracy of cell cycle images was achieved more effectively with our method, reaching 83.88%. Compared with an accuracy of 79.40% in previous experiments, our accuracy increased by 4.48%. Another dataset was used to verify the effect of our model and, compared with the accuracy from previous results, our accuracy increased by 12.52%. The results showed that our new cell cycle image classification system based on WGAN-GP and ResNet is useful for the classification of imbalanced images. Moreover, our method could potentially solve the low classification accuracy in biomedical images caused by insufficient numbers of original images and the imbalanced distribution of original images.

scholarly journals 1D conditional generative adversarial network for spectrum-to-spectrum translation of simulated chemical reflectance signatures

2021 ◽  
Author(s):  
Cara Murphy ◽  
John Kerekes
Keyword(s):  
Classification Accuracy ◽  
Domain Adaptation ◽  
Real Data ◽  
Training Set ◽  
Generative Adversarial Network ◽  
Average Classification Accuracy ◽  
Adversarial Network ◽  
Chemical Residues ◽  
Reflectance Data

The classification of trace chemical residues through active spectroscopic sensing is challenging due to the lack of physics-based models that can accurately predict spectra. To overcome this challenge, we leveraged the field of domain adaptation to translate data from the simulated to the measured domain for training a classifier. We developed the first 1D conditional generative adversarial network (GAN) to perform spectrum-to-spectrum translation of reflectance signatures. We applied the 1D conditional GAN to a library of simulated spectra and quantified the improvement in classification accuracy on real data using the translated spectra for training the classifier. Using the GAN-translated library, the average classification accuracy increased from 0.622 to 0.723 on real chemical reflectance data, including data from chemicals not included in the GAN training set.

scholarly journals Automated classification of blood cell neutrophils.

1977 ◽  
Vol 25 (7) ◽  
pp. 633-640 ◽  
Author(s):  
J K Mui ◽  
K S Fu ◽  
J W Bacus
Keyword(s):  
Blood Cell ◽  
White Blood Cell ◽  
Classification Accuracy ◽  
Three Dimensional ◽  
Classification Problem ◽  
Differential Count ◽  
Two Dimensional ◽  
Automated Classification ◽  
Exact Shape

The classification of white blood cell neutrophils into band neutrophils (bands) and segmented neutrophils (segs) is a subproblem of the white blood cell differential count. This classification problem is not well defined for at least two reasons: (a) there are no unique quantitative definitions for bands and segs and (b) existing definitions use the shape of the nucleus as the only discriminating criterion. When cells are classified on a slide, decisions are made from the two-dimensional views of these three-dimensional cells. A problem arises because the exact shape of the nucleus becomes indeterminate when the nucleus overlaps so that the filament is hidden. To assess the importance of this problem, this paper quantitates the classification errors due to overlapped nuclei (ON). The results indicate that, using only neutrophils without ON, the classification accuracy is 89%. For neutrophils with ON, the classification accuracy is 65%. This suggests a classification strategy of first classifying neutrophils into three categories: (a) bands without ON, (b) segs without ON and (c) neutrophils with ON. Category III can then be further classified into segs and bands by other stretegies.

scholarly journals Automated Classification of Mental Arithmetic Tasks Using Recurrent Neural Network and Entropy Features Obtained from Multi-Channel EEG Signals

Electronics ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 1079
Author(s):  
Abhishek Varshney ◽  
Samit Kumar Ghosh ◽  
Sibasankar Padhy ◽  
Rajesh Kumar Tripathy ◽  
U. Rajendra Acharya
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Classification Accuracy ◽  
Mental Arithmetic ◽  
Cognitive Workload ◽  
Automated Classification ◽  
Eeg Signals ◽  
Arithmetic Task ◽  
Mental Arithmetic Task

The automated classification of cognitive workload tasks based on the analysis of multi-channel EEG signals is vital for human–computer interface (HCI) applications. In this paper, we propose a computerized approach for categorizing mental-arithmetic-based cognitive workload tasks using multi-channel electroencephalogram (EEG) signals. The approach evaluates various entropy features, such as the approximation entropy, sample entropy, permutation entropy, dispersion entropy, and slope entropy, from each channel of the EEG signal. These features were fed to various recurrent neural network (RNN) models, such as long-short term memory (LSTM), bidirectional LSTM (BLSTM), and gated recurrent unit (GRU), for the automated classification of mental-arithmetic-based cognitive workload tasks. Two cognitive workload classification strategies (bad mental arithmetic calculation (BMAC) vs. good mental arithmetic calculation (GMAC); and before mental arithmetic calculation (BFMAC) vs. during mental arithmetic calculation (DMAC)) are considered in this work. The approach was evaluated using the publicly available mental arithmetic task-based EEG database. The results reveal that our proposed approach obtained classification accuracy values of 99.81%, 99.43%, and 99.81%, using the LSTM, BLSTM, and GRU-based RNN classifiers, respectively for the BMAC vs. GMAC cognitive workload classification strategy using all entropy features and a 10-fold cross-validation (CV) technique. The slope entropy features combined with each RNN-based model obtained higher classification accuracy compared with other entropy features for the classification of the BMAC vs. GMAC task. We obtained the average classification accuracy values of 99.39%, 99.44%, and 99.63% for the classification of the BFMAC vs. DMAC tasks, using the LSTM, BLSTM, and GRU classifiers with all entropy features and a hold-out CV scheme. Our developed automated mental arithmetic task system is ready to be tested with more databases for real-world applications.

Multi-classification of action intention understanding brain signals based on thresholding graph metric

2021 ◽  
pp. 1-8
Author(s):  
Qian Cai ◽  
Xingliang Xiong ◽  
Weiqiang Gong ◽  
Haixian Wang
Keyword(s):  
Feature Extraction ◽  
Classification Accuracy ◽  
Binary Classification ◽  
Extraction Procedure ◽  
Graph Metrics ◽  
Brain Signals ◽  
Intention Understanding ◽  
Multi Classification ◽  
Action Intention

BACKGROUND: Classification of action intention understanding is extremely important for human computer interaction. Many studies on the action intention understanding classification mainly focus on binary classification, while the classification accuracy is often unsatisfactory, not to mention multi-classification. METHOD: To complete the multi-classification task of action intention understanding brain signals effectively, we propose a novel feature extraction procedure based on thresholding graph metrics. RESULTS: Both the alpha frequency band and full-band obtained considerable classification accuracies. Compared with other methods, the novel method has better classification accuracy. CONCLUSIONS: Brain activity of action intention understanding is closely related to the alpha band. The new feature extraction procedure is an effective method for the multi-classification of action intention understanding brain signals.

scholarly journals The serum metabolomics signature of type 2 diabetes is obscured in Alzheimer’s disease

2018 ◽  
Vol 314 (6) ◽  
pp. E584-E596 ◽  
Author(s):  
Jill K. Morris ◽  
Brian D. Piccolo ◽  
Kartik Shankar ◽  
John P. Thyfault ◽  
Sean H. Adams
Keyword(s):  
Alzheimer’S Disease ◽  
Type 2 Diabetes ◽  
Alzheimer's Disease ◽  
Classification Accuracy ◽  
Binary Classification ◽  
Metabolic Phenotype ◽  
Primary Metabolism ◽  
Complex Lipids

There is evidence for systemic metabolic impairment in Alzheimer’s disease (AD), and type 2 diabetes (T2D) increases AD risk. Although studies analyzing blood metabolomics signatures have shown differences between cognitively healthy (CH) and AD subjects, these signatures have not been compared with individuals with T2D. We utilized untargeted analysis platforms (primary metabolism and complex lipids) to characterize the serum metabolome of 126 overnight-fasted elderly subjects classified into four groups based upon AD status (CH or AD) and T2D status [nondiabetic (ND) or T2D]. Cognitive diagnosis groups were a priori weighted equally with T2D subjects. We hypothesized that AD subjects would display a metabolic profile similar to cognitively normal elderly individuals with T2D. However, partial least squares-discriminant analysis (PLS-DA) modeling resulted in poor classification across the four groups (<50% classification accuracy of test subjects). Binary classification of AD vs. CH was poor, but binary classification of T2D vs. ND was good, providing >79.5% and >76.9% classification accuracy for held-out samples using primary metabolism and complex lipids, respectively. When modeling was limited to CH subjects, T2D discrimination improved for the primary metabolism platform (>89.5%) and remained accurate for complex lipids (>73% accuracy). Greater abundances of glucose, fatty acids (C20:2), and phosphatidylcholines and lower abundances of glycine, maleimide, octanol, and tryptophan, cholesterol esters, phosphatidylcholines, and sphingomyelins were identified in CH subjects with T2D relative to those without T2D. In contrast, T2D was not accurately discriminated within AD subjects. Results herein suggest that AD may obscure the typical metabolic phenotype of T2D.

scholarly journals Automatic Detection and Classification of Cough Events Based on Deep Learning

2020 ◽  
Vol 6 (3) ◽  
pp. 322-325
Author(s):  
Seyed Amir Hossein Tabatabaei ◽  
Gabriela Augustinov ◽  
Volker Gross ◽  
Keywan Sohrabi ◽  
Patrick Fischer ◽  
...  
Keyword(s):  
Deep Learning ◽  
Classification Accuracy ◽  
Operating Characteristic ◽  
Binary Classification ◽  
Classification Model ◽  
Learning Approach ◽  
Classification Models ◽  
Recording Channels ◽  
Cough Sound

AbstractIn this paper, a deep learning approach for classification of cough sound segments is presented. The architecture of the network is based on a pre-trained network and the spectrogram images of three recording channels have been extracted for the sake of training the network. The classification accuracy based on three recording channels is 92% for a binary classification model and the network converges fast. Two classification models based on binary and multi-class problems are proposed. Relevant classification parameters including the Receiver Operating Characteristic (ROC) curve are reported.

scholarly journals An Artificial Intelligence (AI) Approach for Automated Flow Cytometric Diagnosis of B-Cell Lymphoma

Blood ◽  
2018 ◽  
Vol 132 (Supplement 1) ◽  
pp. 2856-2856 ◽  
Author(s):  
Alexander Höllein ◽  
Max Zhao ◽  
Richard Schabath ◽  
Torsten Haferlach ◽  
Claudia Haferlach ◽  
...  
Keyword(s):  
B Cell ◽  
Classification Accuracy ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Cell Populations ◽  
Automated Classification ◽  
Employment Equity ◽  
Equity Ownership ◽  
Normal Controls

Abstract Background: Multi-parameter flow cytometry (MFC) data is a diagnostic keystone for hematologic malignancies. Data analysis and interpretation requires resources and expertise, full automation is desired. Combination of automated gating strategies and machine learning on MFC data proved effective in detecting AML cell populations vs normal (Aghaeepour et al., 2013). Aim of our approach was to create tools capable of comprehensively analyzing and classifying MFC data. We developed a proof of principle framework to process MFC data generated from samples with suspected B-cell lymphomas. Methods: MFC data was obtained from routine diagnostics of 16,384 patients as follows: normal controls (n=8,493), chronic lymphocytic leukemia (CLL, n=3,412), CLL with increased prolymphocytes (CLL/PL, n=603), follicular lymphoma (FL, n=219), hairy cell leukemia (HCL, n=193), lymphoplasmacytic lymphoma (LPL, n=629), mantle cell lymphoma (MCL, n=269), marginal zone lymphoma (MZL, n=979), monoclonal B-cell lymphocytosis (MBL, n=1,480). Two 9-color combinations of monoclonal antibodies were applied to analyze surface expression of the following antigens besides scatter signals: FMC7, CD10, IgM, CD79b, CD20, CD23, CD19, CD5, CD45, Kappa, Lambda, CD38, CD25, CD11c, CD103, CD22. For dimensionality reduction we used an unsupervised clustering approach (Kohonen et al., 1990). We first generated a consensus self-organizing map (CS) of 100 nodes including all MFC events of multiple preselected cases (5 samples/cohort). For a test case the fluorescent profile of a cell was assigned to its nearest node in the CS (upsampling). We used the resulting distribution for classification by a sequential neural network (NN). Computationally intensive processing steps were run using Amazon Web Services. Mean accuracies were calculated counting individual cases across the entire dataset. All accuracies are described for 10 CS generations and 10-fold cross validation in the classification process. Approaches of data processing were sequentially developed aiming at maximization of classification accuracy. Results: First, we assessed the performance in a binary classification, i.e. the merged group of CLL and MBL (n=4,877) vs. normal (n=8,493) achieving 97% accuracy. Secondly, we applied our approach to the classification of all 9 classes with an accuracy of 74%. Visual inspection of tSNE (van der Maaten et al., 2008) transformed upsampling information revealed good separability between CLL and normal cases but substantial overlap between other lymphoma subtypes (Figure). The following approaches were applied to improve classification: 1) Automated pregating of lymphocytes (CD45/SSC) by DBSCAN analysis (Ester et al., 1996) improved classification. Applying this to both CS generation and upsampling the accuracy of the 9-class problem increased to 78% (p<0.001). 2) Using a CS trained only on cases with unequivocal phenotypes without pregating was significantly better (p=0.01), but pregating overrode this effect (p=0.5). 3) According to the partial overlap of immunophenotypes hierarchical clustering of misclassifications showed overlap mainly between MCL and CLL/PL as well as between LPL and MZL. We therefore changed our approach merging the groups CLL/MBL, MCL/CLL/PL and LPL/MZL while keeping FL, HCL and normal controls separate. Automated classification of these 6 classes resulted in 86% accuracy. 4) Further regrouping into 3 classes, according to the commonly applied routine approach of distinguishing normal cases from CD5+ (CLL, MBL, MCL, CLL/PL) and CD5- B-cell lymphoma (FL, LPL, MZL, HCL) resulted in a classification accuracy of 89%. 5) The misclassified cases in the 3-class experiment had an average infiltration of 10% versus 41% for correctly classified ones. Limiting the automated classification to cases with ≥5% infiltration increased the classification accuracy to 95%. Conclusion: We created a framework for automated classification and analysis of routine diagnostic MFC data. Definition of entities and preselection of cell populations are essential for optimizing classification accuracy. Our approach is the first application of computational MFC and AI on a large scale dataset and proves the feasibility in a routine diagnostic work flow. To further improve the accuracy of classification a future algorithm will integrate distance metrics following SOM generation into the NN classifier. Disclosures Höllein: MLL Munich Leukemia Laboratory: Employment. Schabath:MLL Munich Leukemia Laboratory: Employment. Haferlach:MLL Munich Leukemia Laboratory: Employment, Equity Ownership. Haferlach:MLL Munich Leukemia Laboratory: Employment, Equity Ownership. Kern:MLL Munich Leukemia Laboratory: Employment, Equity Ownership.

Sign in / Sign up

Export Citation Format

Share Document